检索结果-内蒙古大学图书馆

Deep Position-Aware Hashing for Semantic Continuous Image Retrieval

学校读者我要写书评

暂无评论

Deep Position-Aware Hashing for Semantic Continuous Image Re...

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Ruikui Wang Ruiping Wang Shishi Qiao Shiguang Shan Xilin Chen Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China

ISBN: (数字)9781728165530

ISBN: (纸本)9781728165547

Preserving the semantic similarity is one of the most important goals of hashing. Most existing deep hashing methods employ pairs or triplets of samples in training stage, which only consider the semantic similarity within a minibatch and depict the local positional relationship in Hamming space, leading to intermittent semantic similarity preservation. In this paper, we propose Deep Position-Aware Hashing (DPAH) to ensure continuous semantic similarity in Hamming space by modeling global positional relationship. Specifically, we introduce a set of learnable class centers as the global proxies to represent the global information and generate discriminative binary codes by constraining the distance between data points and class centers. In addition, in order to reduce the information loss caused by relaxing the binary codes to real-values in optimization, we propose kurtosis loss (KT loss) to handle the distribution of real-valued features before thresholding to be double-peak, and then enable the real-valued features to be more binarylike. Comprehensive experiments on three datasets show that our DPAH outperforms state-of-the-art methods.

关键词： Semantics Binary codes Training Image retrieval Quantization (signal) Marine vehicles Optimization

CDCONV: A Benchmark for Contradiction Detection in Chinese Conversations

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zheng, Chujie Zhou, Jinfeng Zheng, Yinhe Peng, Libiao Guo, Zhen Wu, Wenquan Niu, Zheng-Yu Wu, Hua Huang, Minlie The CoAI Group Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems India Beijing National Research Center for Information Science and Technology DCST Tsinghua University Beijing100084 China College of Intelligence and Computing Tianjin University Tianjin China Lingxin AI Beijing100084 China Baidu Inc. China

Dialogue contradiction is a critical issue in open-domain dialogue systems. The contextualization nature of conversations makes dialogue contradiction detection rather challenging. In this work, we propose a benchmark for Contradiction Detection in Chinese Conversations, namely CDCONV. It contains 12K multi-turn conversations annotated with three typical contradiction categories: Intra-sentence Contradiction, Role Confusion, and History Contradiction. To efficiently construct the CDCONV conversations, we devise a series of methods for automatic conversation generation, which simulate common user behaviors that trigger chatbots to make contradictions. We conduct careful manual quality screening of the constructed conversations and show that state-of-the-art Chinese chatbots can be easily goaded into making contradictions. Experiments on CDCONV show that properly modeling contextual information is critical for dialogue contradiction detection, but there are still unresolved challenges that require future research. Copyright © 2022, The Authors. All rights reserved.

关键词： Behavioral research

Single-shot spatial-temporal-spectral complex amplitude imaging via wavelength-time multiplexing

学校读者我要写书评

暂无评论

Advanced Photonics 2025年第2期 123-134页

作者： Yingming Xu Chengzhi Jin Liangze Pan Yu He Yunhua Yao Dalong Qi Cheng Liu Junhui Shi Zhenrong Sun Shian Zhang Jianqiang Zhu Research Center for Novel Computational Sensing and Intelligent Processing Zhejiang Lab Chinese Academy of Sciences Shanghai Institute of Optics and Fine Mechanics Key Laboratory of High Power Laser and Physics East China Normal University School of Physics and Electronic Science State Key Laboratory of Precision Spectroscopy South-Central Minzu University College of Electronics and Information Engineering China Jiliang University College of Optical and Electronic Technology

Single-shot ultrafast multidimensional optical imaging(UMOI) combines ultrahigh temporal resolution with multidimensional imaging capabilities in a snapshot, making it an essential tool for real-time detection and analysis of ultrafast scenes. However, current single-shot UMOI techniques cannot simultaneously capture the spatial-temporal-spectral complex amplitude information, hampering it from complete analyses of ultrafast *** address this issue, we propose a single-shot spatial-temporal-spectral complex amplitude imaging(STS-CAI)technique using wavelength and time multiplexing. By employing precise modulation of a broadband pulse via an encoding plate in coherent diffraction imaging and spatial-temporal shearing through a wide-open-slit streak camera, dual-mode multiplexing image reconstruction of wavelength and time is achieved, which significantly enhances the efficiency of information acquisition. Experimentally, a custom-built STS-CAI apparatus precisely measures the spatiotemporal characteristics of picosecond spatiotemporally chirped and spatial vortex pulses, respectively. STS-CAI demonstrates both ultrahigh temporal resolution and robust phase sensitivity. Prospectively, this technique is valuable for spatiotemporal coupling measurements of large-aperture ultrashort pulses and offers promising applications in both fundamental research and applied sciences.

关键词：

A deep learning system for predicting time to progression of diabetic retinopathy

学校读者我要写书评

暂无评论

NATURE MEDICINE 2024年第2期30卷 358-359页

作者： [Anonymous] Shanghai Belt and Road International Joint Laboratory for Intelligent Prevention and Treatment of Metabolic Disorders Department of Computer Science and Engineering School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Department of Endocrinology and Metabolism Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai Diabetes Institute Shanghai Clinical Center for Diabetes Shanghai China MOE Key Laboratory of AI School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Department of Ophthalmology Huadong Sanatorium Wuxi China Department of Ophthalmology Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai China Department of Ophthalmology and Visual Sciences The Chinese University of Hong Kong Hong Kong China Singapore Eye Research Institute Singapore National Eye Centre Singapore Singapore Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong China Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong China State Key Laboratory of Ophthalmology Zhongshan Ophthalmic Center Sun Yat-sen University Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science Guangzhou China Department of Ophthalmology Peking Union Medical College Hospital Peking Union Medical College Chinese Academy of Medical Sciences Beijing China Medical Records and Statistics Office Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai China Department of Geriatrics Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Tech

We developed and validated a deep learning system (termed DeepDR Plus) in a diverse, multiethnic, multi-country dataset to predict personalized risk and time to progression of diabetic retinopathy. We show that DeepDR Plus can be integrated into the clinical workflow to promote individualized intervention strategies for the management of diabetic retinopathy.

关键词： Diabetes complications Machine learning Predictive markers

Meta ordinal weighting net for improving lung nodule classification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lei, Yiming Shan, Hongming Zhang, Junping Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Institute of Science and Technology for Brain-inspired Intelligence Fudan University Shanghai200433 China

The progression of lung cancer implies the intrinsic ordinal relationship of lung nodules at different stages—from benign to unsure then to malignant. This problem can be solved by ordinal regression methods, which is between classification and regression due to its ordinal lab.l. However, existing convolutional neural network (CNN)-based ordinal regression methods only focus on modifying classification head based on a randomly sampled mini-batch of data, ignoring the ordinal relationship resided in the data itself. In this paper, we propose a Meta Ordinal Weighting Network (MOW-Net) to explicitly align each training sample with a meta ordinal set (MOS) containing a few samples from all classes. During the training process, the MOW-Net learns a mapping from samples in MOS to the corresponding class-specific weight. In addition, we further propose a meta cross-entropy (MCE) loss to optimize the network in a meta-learning scheme. The experimental results demonstrate that the MOW-Net achieves better accuracy than the state-of-the-art ordinal regression methods, especially for the unsure class. © 2021, CC BY.

关键词： Convolutional neural networks

Universal Deep GNNs: Rethinking Residual Connection in GNNs from a Path Decomposition Perspective for Preventing the Over-smoothing

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Jie Liu, Weiqi Huang, Zhizhong Gao, Junbin Zhang, Junping Pu, Jian Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Discipline of Business Analytics The University of Sydney Business School The University of Sydney SydneyNSW2006 Australia Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai200433 China

The performance of GNNs degrades as they become deeper due to the oversmoothing. Among all the attempts to prevent over-smoothing, residual connection is one of the promising methods due to its simplicity. However, recent studies have shown that GNNs with residual connections only slightly slow down the degeneration. The reason why residual connections fail in GNNs is still unknown. In this paper, we investigate the forward and backward behavior of GNNs with residual connections from a novel path decomposition perspective. We find that the recursive aggregation of the median length paths from the binomial distribution of residual connection paths dominates output representation, resulting in over-smoothing as GNNs go deeper. Entangled propagation and weight matrices cause gradient smoothing and prevent GNNs with residual connections from optimizing to the identity mapping. Based on these findings, we present a Universal Deep GNNs (UDGNN) framework with cold-start adaptive residual connections (DRIVE) and feedforward modules. Extensive experiments demonstrate the effectiveness of our method, which achieves state-of-the-art results over non-smooth heterophily datasets by simply stacking standard GNNs. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

Epilepsy Classification for Mining Deeper Relationships between EEG Channels based on GCN

学校读者我要写书评

暂无评论

Epilepsy Classification for Mining Deeper Relationships betw...

2020 International Conference on Computer Vision, Image and Deep Learning, CVIDL 2020

作者： Chen, Xin Zheng, Yuanjie Niu, Yi Li, Chengiiang Shandong Normal University School of Information Science and Engineering Jinan250358 China Key Lab of Intelligent Computing and Information Security Universities of Shandong Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Institute of Biomedical Sciences Jinan250358 China Department of Electrical Engineering Information Technology Shandong University of Science and Technology Jinan250031 China

ISBN: (纸本)9781728194813

Epilepsy is a brain disorder caused by abnormal discharges of neurons in brain. It is one of the most commonly studied disorders in neurology. The research of epilepsy electroencephalogram (EEG) has become a hot research topic. We find that in epilepsy EEG detection task, many previous methods focused on directly collecting the data of each channel, but these methods seldom analyse relationships between signals. Therefore, we propose the Epilepsy EEG Graph Convolutional Network EGCN, which makes full use of correlations between channels to deeply mine data information. We specifically design 5-layer graph convolutional network structure for classification of healthy and epileptic patients. The method is applied to public data set (Boon and CHB-MIT) to establish a reasonable classification model. And we compare it with some advanced algorithms. The experimental results show that the E-GCN method is superior to many existing methods in classification accuracy. In brief, the E-GCN method can be effectively used in classification and detection for epilepsy. This provides new ideas for colleagues, who study epilepsy EEG. In addition, this also provides richer experience for diagnosis of epilepsy. © 2020 IEEE.

关键词： Electroencephalography

Steady-state Analysis of Bipolar Transistor

学校读者我要写书评

暂无评论

Steady-state Analysis of Bipolar Transistor

Progress in Electromagnetic Research Symposium (PIERS)

作者： Yeqiang Yan Xingang Ren Shuping He Xiaotao Huang Zhixiang Huang Anhui Province Key Laboratory of Target Recognition and Feature Extraction Luan China Information Materials and Intelligent Sensing Laboratory of Anhui Province Institute of Physical Science and Information Technology Anhui University Hefei China Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China Lingnan Normal University Zhanjiang China

ISBN: (纸本)9781665409889

Numerical simulation of semiconductor devices enable the quick obtain of the device physical characteristics. However, the trial productions of the semiconductor devices have the disadvantages of long cycle and high cost. Therefore, it is necessary to carry out numerical simulation investigating semiconductor devices. We propose the coupling approach and the decoupling-Gummel method to solve the semiconductor equations. The results of the two methods are compared with the commercial software. Numerical experiment indicates that the results obtained by our method are accurate. When the transistor is at a low voltage bias, the decoupling method converges faster than the coupling method. In the case of high voltage bias, the decoupling method has a slower convergence speed than the coupling method, even difficult to converge for higher voltage bias. However, the coupling method has higher memory requirements than the Gummel method. Therefore, we need to balance the advantages of the coupling method and the Gummel method when conduct the numerical simulation.

关键词： Couplings Bipolar transistors Voltage Production Numerical simulation Mathematical models Software

Large Generative Model Assisted 3D Semantic Communication

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jiang, Feibo Peng, Yubo Dong, Li Wang, Kezhi Yang, Kun Pan, Cunhua You, Xiaohu Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China School of Information Science and Engineering Hunan Normal University Changsha China Changsha Social Laboratory of Artificial Intelligence Hunan University of Technology and Business Changsha China The Department of Computer Science Brunel University London United Kingdom The School of Computer Science and Electronic Engineering University of Essex ColchesterCO4 3SQ United Kingdom Changchun Institute of Technology China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The Frontiers Science Center for Mobile Information Communication and Security National Mobile Communications Research Laboratory Southeast University Nanjing China The Purple Mountain Laboratories Nanjing China

Semantic Communication (SC) is a novel paradigm for data transmission in 6G. However, there are several challenges posed when performing SC in 3D scenarios: 1) 3D semantic extraction;2) Latent semantic redundancy;and 3) Uncertain channel estimation. To address these issues, we propose a Generative AI Model assisted 3D SC (GAM-3DSC) system. Firstly, we introduce a 3D Semantic Extractor (3DSE), which employs generative AI models, including Segment Anything Model (SAM) and Neural Radiance Field (NeRF), to extract key semantics from a 3D scenario based on user requirements. The extracted 3D semantics are represented as multi-perspective images of the goal-oriented 3D object. Then, we present an Adaptive Semantic Compression Model (ASCM) for encoding these multi-perspective images, in which we use a semantic encoder with two output heads to perform semantic encoding and mask redundant semantics in the latent semantic space, respectively. Next, we design a conditional Generative adversarial network and Diffusion model aided-Channel Estimation (GDCE) to estimate and refine the Channel State information (CSI) of physical channels. Finally, simulation results demonstrate the advantages of the proposed GAM-3DSC system in effectively transmitting the goal-oriented 3D scenario. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics